© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7211
    Prev
    Next
    INDEX
    Explanations

    text describing the steps and components of algorithms

    oai_token-act-pair · gemini-2.0-flash

    mathematical/scientific writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LIRE
    -0.59
     Paix
    -0.53
     Hake
    -0.52
    asteroide
    -0.51
     Catawiki
    -0.50
     typelib
    -0.50
     Anſ
    -0.49
    œurs
    -0.49
    icordia
    -0.49
    참고
    -0.49
    POSITIVE LOGITS
    ftagPool
    0.68
    AnimationsModule
    0.54
     GenerationType
    0.54
    ̈́
    0.51
    StatusBadRequest
    0.48
    seitige
    0.48
     total
    0.47
     للمعارف
    0.47
    GraphicsUnit
    0.47
    endlich
    0.46
    Activations Density 4.155%

    No Known Activations